Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    strain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pagamento
    -0.07
    =row
    -0.07
    DISPLAY
    -0.06
    nutím
    -0.06
    点
    -0.06
    761
    -0.06
    ha
    -0.06
     turtle
    -0.06
    \model
    -0.06
     participation
    -0.06
    POSITIVE LOGITS
     курс
    0.07
     κ
    0.06
    .setParameter
    0.06
     knobs
    0.06
     QU
    0.06
     Gry
    0.06
     mourn
    0.06
    ียง
    0.06
    048
    0.06
     Edmund
    0.06
    Act Density 0.006%

    No Known Activations